Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    once

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scattering
    -0.08
    antwort
    -0.07
     w
    -0.06
     Pandora
    -0.06
     Carla
    -0.06
     hưởng
    -0.06
     сф
    -0.06
     m
    -0.06
     btn
    -0.06
     seinem
    -0.06
    POSITIVE LOGITS
     Once
    0.13
    Once
    0.12
     once
    0.11
    once
    0.09
    .Once
    0.08
     Hayes
    0.08
     Exclusive
    0.08
    ок
    0.08
    oncé
    0.07
     Twice
    0.07
    Act Density 0.021%

    No Known Activations